KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 10

Some of the metrics are blocked by your
consent settings
Improved Rerun Particle Swarm Optimization Algorithm with Harmony Search
(2019-04-10)
Phuchan, Wikrom
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
One of the most crucial problem of the particle swarm optimization is that it can easily trap in local optima. There are some studies tried to resolve the drawback using the reset and mutation mechanism. Although it unraveled the problem well when the optimal position of benchmark function is at zeros in all dimensions. It cannot locate optima when the exact answer randomly shifted over the possible region. This study integrates Harmony Search (HS) to the rerun and reset mechanism to PSO. It performs well with selected benchmark functions, when the optimal position is randomly shifted in most of the test functions. Since it does not favor optimal point at zeroes when the optimal position is not shifted, the number of calls of the evaluation function is more than the other algorithms in some cases.
Some of the metrics are blocked by your
consent settings
Enhance particle's exploration of particle swarm optimization with individual particle mutation
(2019-03-01)
Adsawinnawanawa, Ekkarat
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed the restart of slow improvement particle with Mutation of its position. This can alleviate the trapped in local optima problem of Particle swarm optimization (PSO). The main characteristic of this method is the gradually restart of particle instead of restart all particle at the same time (rerun). This seems to maintain fast convergence of PSO and avoid overhead of restart the whole swarm. The performance of the proposed method is compared to others algorithms with 26 benchmark test functions. The results confirm the faster convergence with optimum results of the proposed method in most test functions.
Some of the metrics are blocked by your
consent settings
Improving Multi-Swarm by Slightly Mutation Particle and GBEST of Stuck Swarm Along with Randomly Selecting GBEST of Other Swarm
(2018-08-21)
Chengkhuntod, Kanokporn
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed another approach in handling trapping in local optimum problem of Particle Swarm Optimization (PSO) using multi-swarm. Since each swarm might trap in different local optimum, the trapped swarm restart with slightly mutation (15% of each particle attributes) along with swaying swarm by randomly use of other swarm GBEST position. In the case of all swarm trapping in the same location, the trap GBEST is also slightly mutate in the same way as particle position. This proposed technique is tested on a set of twenty-four benchmark test functions. The experimental results show that the proposed method is better than other comparing methods.
Some of the metrics are blocked by your
consent settings
Combine multi particle swarm in supporting trapping in local optima
(2018-08-13)
Poempool, Lukkana
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed using multi swarm to lessen trapping in local optima problem of Particle Swarm Optimization (PSO). The use of multiple swarms can increase wider global search at the cost of decrease narrower local search. Hence, the use of multiple swarms alone can't solve the trapping problem. This paper extends the use of multi swarm by merging all the swarm into single group to enhanced local search when needed. This can increase the local search ability of multi swarm and increase the chance of the trapped swarm to move to other nearby local optima. The proposed method is compared to similarly comparable modified PSO and other similarly multi particle swarm without merging using 26 benchmark functions.
Some of the metrics are blocked by your
consent settings
The use of global best position in rerun of particle swarm optimization
(2018-08-13)
Cheypoca, Varothon
;
Siriboon, Kritawan
;
Kruatrachue, Boontee
This paper studies the use of particle best position (GBEST) in rerun when particle swarm optimization (PSO) traps in local optima. Reinitialize particles positions are often used to restart PSO to get better results when trapping in local optima. This paper proposed the use of GBEST to further force particle movement out of previous local optima instead of only reset GBEST. The proposed method is tested on 26 benchmark test functions with satisfactory results.
Some of the metrics are blocked by your
consent settings
Hybrid multi-swarm with Harmony Search algorithm
(2017-11-03)
Phuchan, Wikrom
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
This paper proposed a new metaheuristic algorithm, Hybrid Multi-swarm with Harmony Search algorithm which combines two famous metaheuristics, particle swarm optimization (PSO) and Harmony Search algorithm (HS). The main advantage of PSO is its convergence speed while its main drawback is trapping in local optimum problem. To improve PSO performance, this research use HS to increase PSO diversity and extend its convergence point to a better local optimum. The proposed algorithm was compared with three related algorithms on the optimization benchmark functions. The experiment results show the proposed algorithm yields better fitness value solution.
Some of the metrics are blocked by your
consent settings
A modified multi-swarm optimization with interchange GBEST and particle redistribution
(2017-10-19)
Chengkhuntod, Kanokporn
;
Kruatrachue, Boontee
;
Siriboon, Kritawan
The Particle Swarm Optimization (PSO) is an optimization algorithm using multiples particle to search solution space for an optimize solution. Each particle of PSO moves toward the best solution within its group. For this behavior, PSO often traps in local optimum. Many researchers proposed splitting a swarm into multiple swarms so that they may move to different local optimum. Besides, the mutation operation technique, the natural selection technique and the crossover operation technique are added to normal PSO process. These proposed techniques are called Selective Crossover base on Fitness in Multi-Swarm Optimization (SFMPSO) and Fast Multi-swarm Optimization (FMPSO). However, both techniques used too many evaluation calls dues to crossover and the mutation operation. This paper proposes setting the best position (GBEST) of a trapped swarm to GBEST of the other swarm. Then, the swarm's particle is redistributed in solution space before restart the trapped swarm. This proposed technique is evaluated on a set of twenty-six benchmark test functions. The experimental results show that the results are better than those of PSO, FMPSO and SFMPSO.
Some of the metrics are blocked by your
consent settings
State machine induction with positive and negative training for thai character recognition
(2008-03-18)
Kruatrachue, Boontee
;
Pantrakarn, Nattachat
;
Siriboon, Kritawan
One problem of generating a model to recognize any string is how to generate one that is generalized enough to accept strings with similar patterns and, at the same time, is specific enough to reject the non-target strings. This research focus on generating a model in the form of a state machine to recognize strings derived from the direction information of character's images. The state machine induction process has two steps. The first step is to generate the machine from the strings of each target character (Positive Training), and the second step is to adjust the machine to reject any other string (Negative Training). This state machine induction method that automatically learns from strings can be applied with other string patterns recognition apart from characters.
Some of the metrics are blocked by your
consent settings
Fast document segmentation using contour and X-Y cut technique
(2005-12-01)
Kruatrachue, Boontee
;
Moongfangklang, Narongchai
;
Siriboon, Kritawan
This paper describes fast and efficient method for page segmentation of document containing nonrectangular block. The segmentation is based on edge following algorithm using small window of 16 by 32 pixels. This segmentation is very fast since only border pixels of paragraph are used without scanning the whole page. Still, the segmentation may contain error if the space between them is smaller than the window used in edge following. Consequently, this paper reduce this error by first identify the missed segmentation point using direction information in edge following then, using X-Y cut at the missed segmentation point to separate the connected columns. The advantage of the proposed method is the fast identification of missed segmentation point. This methodology is faster with fewer overheads than other algorithms that need to access much more pixel of a document. COPYRIGHT © ENFORMATIKA.
Some of the metrics are blocked by your
consent settings
HMM Parameters Optimization using Combine Genetic Algorithm and Iterative Training
(2003-12-01)
Kruatrachue, Boontee
;
Siriboon, Kritawan
;
Nootyaskool, Supakit
HMM have been used extensively for recognizing observation sequence especially in speech recognition. Iterative training procedure such as Baum-Weltch, or gradient techniques are normally used to find locally optimize HMM parameters. This paper presents genetic algorithm (GA) to perform global search for Hidden Markov Model (HMM) parameters that maximize probability of observation sequence given the model. In order to increase the convergence rate and parameters optimization, we combine iterative procedure with GA. The probability of observation sequence of the train model using iterative procedure, GA, and GA with iterative procedure will be compared along with their convergence rates. The test patterns are chain code sequences generated from 38 isolated on-line Thai handwritten characters. The recognition rate and the probability of the train observation sequences of GA were better than the iterative training. The recognition rate of HMM with iterative training 95.05%, GA 97.50% and GA with iterative training 98.41% on 3839 patterns.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results